[ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
☆91Jan 19, 2025Updated last year
Alternatives and similar repositories for VLGuard
Users that are interested in VLGuard are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Accepted by ECCV 2024☆222Oct 15, 2024Updated 2 years ago
- The reinforcement learning codes for dataset SPA-VL☆48Jun 24, 2024Updated 2 years ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆219Jun 26, 2025Updated last year
- [ICML 2024] Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations☆15Oct 28, 2023Updated 3 years ago
- ☆86Mar 30, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated 2 years ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆39Nov 2, 2024Updated 2 years ago
- Accepted by IJCAI-24 Survey Track☆236Aug 25, 2024Updated 2 years ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆62Jul 21, 2025Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆46Apr 21, 2024Updated 2 years ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆95Jun 6, 2024Updated 2 years ago
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆21Mar 31, 2025Updated last year
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆288May 13, 2024Updated 2 years ago
- ☆46Jun 19, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR 2026] Data and Code for Paper Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models☆14Feb 2, 2026Updated 9 months ago
- [ICLR26] Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning☆21Apr 16, 2026Updated 7 months ago
- ☆21Oct 25, 2024Updated 2 years ago
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆34Jul 20, 2025Updated last year
- ☆74Sep 30, 2025Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆72Feb 9, 2026Updated 9 months ago
- ☆13Sep 29, 2025Updated last year
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆91Nov 28, 2023Updated 2 years ago
- Code for Representation Bending Paper☆16Jul 15, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- This is the official repository for Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models.☆17Jan 16, 2025Updated last year
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆102May 9, 2025Updated last year
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆38Jun 23, 2025Updated last year
- [CVPR 2025] Official implementation for JOOD "Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy"☆21Jun 11, 2025Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆43Oct 17, 2024Updated 2 years ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆62Aug 8, 2024Updated 2 years ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated 2 years ago
- ☆62Jun 5, 2024Updated 2 years ago
- A Task of Fictitious Unlearning for VLMs☆27Apr 6, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆96May 9, 2024Updated 2 years ago
- [NeurIPS, 500+ Citations!] Alignment & Safety for multimodal foundation models☆234Nov 1, 2026Updated 3 weeks ago
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆15Apr 8, 2025Updated last year
- Your finetuned model's back to its original safety standards faster than you can say "SafetyLock"!☆11Oct 16, 2024Updated 2 years ago
- [ICLR 2025] Official implementation for "SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanati…☆45Feb 11, 2025Updated last year
- AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models☆14Jun 2, 2025Updated last year
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆65Apr 29, 2026Updated 6 months ago
Are these results useful?